mirekphd/whisper-large-v3-onnx-w8a16-dynamic
By mirekphd · ↓ 0 · ♥ 0 · Updated 2025-07-19
What's in this repo
This page lists the files in mirekphd/whisper-large-v3-onnx-w8a16-dynamic, including decoder_model.onnx, decoder_with_past_model.onnx, encoder_model.onnx.
- 3 ONNX models (.onnx files)
- 14 files, including 8 .json, 3 .onnx, 1 .md, 1 .txt
- Last updated 2025-07-19
ONNX files
| File | Size | Download |
|---|---|---|
| decoder_model.onnx | — | Download |
| decoder_with_past_model.onnx | — | Download |
| encoder_model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
license: mit tags:
- automatic-speech-recognition
- whisper
- onnx
- quantized
ONNX version of whisper-large-v3-onnx-w8a16-dynamic
This repository contains the ONNX version of the openai/whisper-large-v3 model.
Model Details
The original model can be found here: openai/whisper-large-v3
Quantization
This model has been quantized to w8a16 using dynamic quantization. This reduces the model size and can improve inference speed, especially on CPUs.
Usage
The model can be used with optimum.onnxruntime.ORTModelForSpeechSeq2Seq.
from optimum.onnxruntime import ORTModelForSpeechSeq2Seq
from transformers import WhisperProcessor
model_name = "mirekphd/whisper-large-v3-onnx-w8a16-dynamic"
processor = WhisperProcessor.from_pretrained(model_name)
model = ORTModelForSpeechSeq2Seq.from_pretrained(model_name)
# ... add your inference code here ...
Model info
Created: 2025-07-19
Updated: 2025-07-19
View on Hugging Face